US 11,734,882 B2
Machine learning based object identification using scaled diagram and three-dimensional model
Michael Ben Fleischman, San Francisco, CA (US); Gabriel Hein, Albany, CA (US); Thomas Friel Allen, El Ceritto, CA (US); and Abraham Botros, San Francisco, CA (US)
Assigned to Open Space Labs, Inc., San Francisco, CA (US)
Filed by Open Space Labs, Inc., San Francisco, CA (US)
Filed on Jul. 27, 2022, as Appl. No. 17/875,388.
Application 17/875,388 is a continuation of application No. 17/225,802, filed on Apr. 8, 2021, granted, now 11,436,812.
Claims priority of provisional application 63/032,452, filed on May 29, 2020.
Prior Publication US 2022/0375183 A1, Nov. 24, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 19/00 (2011.01); G06T 17/00 (2006.01); G06T 19/20 (2011.01); G06T 17/05 (2011.01); G06T 7/70 (2017.01); G06T 7/11 (2017.01); G06N 20/00 (2019.01); G01S 17/89 (2020.01); G06V 20/40 (2022.01); G06V 30/262 (2022.01); G06F 18/24 (2023.01); G06F 18/214 (2023.01); G06V 20/56 (2022.01)
CPC G06T 17/00 (2013.01) [G01S 17/89 (2013.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06N 20/00 (2019.01); G06T 7/11 (2017.01); G06T 7/70 (2017.01); G06T 17/05 (2013.01); G06T 19/20 (2013.01); G06V 20/41 (2022.01); G06V 20/56 (2022.01); G06V 30/274 (2022.01); G06T 2200/24 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2219/2004 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing a model of a portion of a building, the model indicating locations of one or more expected objects within the portion of the building;
receiving, from a camera system, a video comprising a plurality of image frames captured as the camera system is moved through the portion of the building;
identifying one or more objects in the plurality of image frames at one or more locations within the portion of the building;
determining, for one or more locations within the portion of the building, a count difference between a number of the one or more expected objects from the accessed model and a number of one or more objects identified in the plurality of image frames; and
modifying an interface displayed to a user to present, at each of the one or more locations within the portion of the building, the determined count difference.